论文标题
Dhari向Epic-Kitchens的报告2020对象检测挑战
DHARI Report to EPIC-Kitchens 2020 Object Detection Challenge
论文作者
论文摘要
在本报告中，我们描述了我们对Epic-Kitchens对象检测挑战的提出的技术细节。首先引入Duck填充和混合技术来增强数据并显着提高所提出方法的鲁棒性。然后，我们提出了GRE-FPN和Hard Iou-iou-nou-ntarance Sampler方法，以提取更具代表性的全局对象特征。为了弥合类别不平衡的差距，使用类平衡抽样，并大大改善了测试结果。此外，还利用了一些培训和测试策略，例如随机重量平均和多尺度测试。实验结果表明，我们的方法可以显着提高对象检测的平均平均精度（MAP）在观察和看不见的Epickitchens的测试集上。
In this report, we describe the technical details of oursubmission to the EPIC-Kitchens Object Detection Challenge.Duck filling and mix-up techniques are firstly introduced to augment the data and significantly improve the robustness of the proposed method. Then we propose GRE-FPN and Hard IoU-imbalance Sampler methods to extract more representative global object features. To bridge the gap of category imbalance, Class Balance Sampling is utilized and greatly improves the test results. Besides, some training and testing strategies are also exploited, such as Stochastic Weight Averaging and multi-scale testing. Experimental results demonstrate that our approach can significantly improve the mean Average Precision (mAP) of object detection on both the seen and unseen test sets of EPICKitchens.
